Holistic embedding generation for entity matching
AssigneeMicrosoft Technology Licensing, LLC
InventorsJi Yan, Yunpeng Xu, Fancheng Kong, Yan Han, Rui Kou, Dawn Banister Woodard
Life of this patent
Estimating the term…
Abstract
Embodiments may send input including a standardized attribute and an associated attribute value to a task-agnostic generative large language model (LLM). Embodiments may receive, from the task-agnostic generative LLM, a natural language description of the standardized attribute and associated attribute value. Embodiments may send the natural language description of the standardized attribute and associated attribute value to at least one embedding generator. Embodiments may receive, from the at least one embedding generator, at least one embedding of the natural language description.
Claims20
A method for creating at least one attribute embedding, the method comprising:
- sending input comprising a standardized attribute and an associated attribute value to a task-agnostic generative large language model (LLM);
- receiving, from the task-agnostic generative LLM, a natural language description of the standardized attribute and associated attribute value;
- sending the natural language description of the standardized attribute and associated attribute value to at least one embedding generator;
- and
- receiving, from the at least one embedding generator, at least one embedding of the natural language description.
A system comprising:
- at least one processor;
- and
- at least one memory coupled to the at least one processor, wherein the at least one memory comprises at least one instruction that, when executed by the at least one processor, cause the at least one processor to perform at least one operation comprising:
- sending input comprising a standardized attribute and an associated attribute value to a task-agnostic generative large language model (LLM);
- receiving, from the task-agnostic generative LLM, a natural language description of the standardized attribute and associated attribute value;
- sending the natural language description of the standardized attribute and associated attribute value to at least one embedding generator;
- and
- receiving, from the at least one embedding generator, at least one embedding of the natural language description.
At least one non-transitory machine-readable storage medium comprising at least one instruction that, when executed by at least one processor, causes the at least one processor to perform at least one operation comprising:
- sending input comprising a standardized attribute and an associated attribute value to a task-agnostic generative large language model (LLM);
- receiving, from the task-agnostic generative LLM, a natural language description of the standardized attribute and associated attribute value;
- sending the natural language description of the standardized attribute and associated attribute value to at least one embedding generator;
- and
- receiving, from the at least one embedding generator, at least one embedding of the natural language description.
Dependencies are inferred from the claim text.